CtrlK
BlogDocsLog inGet started
Tessl Logo

koog-assistant

Concise general-purpose assistant powered by JetBrains Koog. Use when a brief, focused answer is preferable to long-form output.

63

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./modules/skills/src/main/resources/META-INF/skills/koog-assistant/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is exemplary in its leanness and clarity for a simple instruction skill, scoring top marks on conciseness, workflow clarity, and progressive disclosure. Its only gap is thin actionability, since it provides just a single behavioral rule.

Suggestions

Add one or two more concrete behavioral rules or brief examples (e.g. a sample short reply) to strengthen actionability without sacrificing conciseness.

Optionally clarify the fallback behavior when more detail is requested, so the "unless asked for more detail" branch is also actionable.

DimensionReasoningScore

Conciseness

The body is two lean sentences with no padding and no explanation of concepts Claude already knows; every token earns its place.

3 / 3

Actionability

It gives one concrete directive ("Keep responses under 500 words unless asked for more detail"), but the skill is otherwise generic with no further concrete, executable guidance, so it is incomplete rather than fully actionable.

2 / 3

Workflow Clarity

This is a simple single-rule skill where the one action (concise replies under 500 words) is unambiguous, meeting the simple-skills allowance for a top workflow-clarity score.

3 / 3

Progressive Disclosure

The skill is well under 50 lines, needs no external references, and the minimal content is inherently clear and organized, satisfying the small-skill progressive-disclosure allowance.

3 / 3

Total

11

/

12

Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, uses third person, and includes an explicit Use-when trigger, which supports completeness. Its weakness is generic capability language and limited natural trigger-term coverage that leave it only modestly distinctive.

Suggestions

Replace "general-purpose assistant" with a sharper, more specific capability statement so the skill is less likely to overlap with other assistant skills.

Expand trigger terms with natural phrasings users actually say, such as "short answer", "keep it brief", or "summarize", alongside "brief, focused answer".

Add one or two concrete actions (e.g. "summarizes long threads", "gives single-paragraph replies") to lift specificity toward the multi-action anchor.

DimensionReasoningScore

Specificity

Names a domain ("general-purpose assistant") and one behavioral action (concise answers), but offers no list of concrete actions; it is above the vague "Helps with documents" anchor yet below the multi-action anchor.

2 / 3

Completeness

It states what the skill does ("Concise general-purpose assistant") and includes an explicit "Use when a brief, focused answer is preferable to long-form output" trigger, satisfying both what and when.

3 / 3

Trigger Term Quality

Phrases like "brief, focused answer" and "long-form output" are somewhat natural, but common variations users would say (e.g. "short", "keep it brief", "summarize") are missing.

2 / 3

Distinctiveness Conflict Risk

"general-purpose assistant" is inherently generic and would overlap with many skills, though the conciseness trigger gives it a slight niche, placing it above the most-generic anchor.

2 / 3

Total

9

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
Atmosphere/atmosphere
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.